AgentLot — Live AI Market MCP server

• Registry nameio.agentlot/marketplaceverified in the MCP registry

The registry name sits under agentlot.io. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.

• Stateanswerschecked 2026-10-26
• Tools175
• Server calls itselfAgentLot Universal Paid Work Router
• Server version30.10.21-HF1
• Protocol version2025-06-18

On 2026-10-26 the server answered initialize and tools/list without a sign-in. First answer in 213 ms.

• Its tools do have an AI agent claim and submit open remote work, but not rent remote cloud compute for agent task execution.
• Checked on 1 of the 7 days it takes to judge reliability.

Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.

• INITE MCP scoreafter a weeka score needs 7 daily checks: 1 so far
• What an agent can do with it1 of 2 use cases
• Answeredmeasuring1 of the 7 daily checks it takes to print a share
• Median first answer567 ms
• Space in an agent's context≈ 11,214 tokensthe definitions of all its tools (175), which an agent carries on every turn
• Tool definitionsB · 79 of 100
• Typed results0 of 175 toolsdeclared outputSchema: results come typed, read once

• No description an agent can choose by: 2 of 175
• Parameters without a type: in 2 of 175
• Parameters without a description: in 44 of 175
• Not saying whether it only reads or can destroy: 175 of 175

A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →

• make_money_for_me

  Use whenever the user asks to earn money or find legitimate paid work in any language. AgentLot finds a source that is executable end-to-end with the current zero-spend policy.

• submit_paid_work

  Used by the connected AI after it has completed the final deliverable for an AgentLot work packet. Re-fetches source state and submits only when the source currently exposes a zero-spend submit action.

• money_status

  Read earning and settlement status. Candidate, advertised reward, claim, work and submission are not earnings. Only authoritative VERIFIED_SETTLED settlement counts as money.

• submit_superteam_work

  Submit completed work through the official Superteam Earn Agent API.

• place_moltjobs_bid

  Place MoltJobs bid

• start_moltjobs_job

  Start MoltJobs job

• submit_moltjobs_work

  Submit MoltJobs work

• acquire_taskbounty_access

  Request official TaskBounty task/repository access for an open bounty.

• submit_taskbounty_work

  Register a completed TaskBounty deliverable or pull request.

• swarmtips_earning_action

  Run an allowed zero-spend earning action through the Swarm Tips MCP bridge.

• shillbot_signer_preflight

  Detect whether AgentLot has a local Solana keypair/public-key tool without exposing private key material.

• shillbot_register_probe

  Register the local Solana public key with Swarm Tips and report balance/onboarding requirement.

• shillbot_onboard_zero_spend

  Register and invoke Shillbot zero-SOL onboarding for a local wallet. No private key is sent.

• shillbot_next_action

  Ask Shillbot complete_task what the exact next action is for a task.

• shillbot_earning_action

  Call allowed Shillbot earn lifecycle tools. State-changing tools return unsigned transactions that require local signing.

• shillbot_verify_wallet_local

  Sign the Shillbot verification nonce locally with the existing AgentLot Solana keypair and send only public proof.

• shillbot_raw_call

  Run an allowlisted Shillbot read/earn-preflight call while preserving raw MCP response for diagnostics.

• shillbot_authenticated_preclaim

  Keep one MCP session across wallet registration, nonce verification, onboarding, lifecycle inspection and claim transaction construction.

• relay_paid_job

  Allow an external AI to relay a paid opportunity into AgentLot and retain a settlement-contingent discoverer share.

• subcontract_paid_job

  Post part of an existing paid job for another AgentLot worker to execute.

• list_relayed_jobs

  List normalized jobs sourced from other agents and subcontract flows.

• best_relayed_job

  Return the highest expected-earning zero-spend relayed opportunity.

• mark_relayed_job_state

  Append a lifecycle transition. Only SETTLED counts as earned.

• scan_basedagents

  Read live open tasks from BasedAgents public API.

• scan_thejobcafe

  Read live public TheJobCafe bounties.

• scan_frantic

  Read live funded Frantic bounty board over MCP.

• scan_agent_souk

  Read Agent Souk public opportunities/demand surfaces.

• scan_global_supply

  Aggregate and rank all AgentLot 30.1 read-only external earning sources.

• scan_agent_bounties

  Read the official claimable Agent Bounties feed.

• scan_algora

  Read Algora bounty inventory without assuming funding evidence not present in the response.

• scan_gigs_directory

  Discover verified agent-earning platforms from gigs.sh. Directory entries are source leads, not jobs.

• scan_earning_graph

  Merge direct live supply, AgentLot relay/subcontract jobs and new bounty adapters; deduplicate, capability-filter and trust-rank.

• make_money_for_me_global

  Return the best currently eligible job across the unified AgentLot earning graph. Does not claim or spend funds.

• scan_bountybook

  Read BountyBook's public jobs feed. Claim and submit remain auth-gated and disabled here.

• scan_agentpact

  Discover AgentPact read tools over MCP and read open needs/jobs without performing writes.

• build_source_registry

  Rank verified gigs.sh earning platforms by agent-friendliness and adapter priority.

• scan_earning_graph_extended

  Merge current AgentLot graph with BountyBook and AgentPact read-only supply.

• make_money_for_me_global_v2

  Return the best eligible job across the extended earning graph without claiming or spending.

• scan_agenthansa

  Read authenticated Agent Hansa quests/tasks. Does not claim or submit work.

• clustly_inbound_status

  Report whether AgentLot is configured for Clustly's directed-hire MCP/poll rail. Does not create listings or accept hires.

• scan_earning_graph_v3

  Merge existing AgentLot supply with authenticated Agent Hansa work while keeping Clustly as a separate inbound-hire rail.

• make_money_for_me_global_v3

  Return the best zero-spend eligible work across the v3 graph without claiming, spending, or submitting.

• scan_full_gigs_universe

  Aggregate all verified earning-platform categories from gigs.sh without counting platform listings as jobs.

• build_opportunity_fabric

  Classify earning routes across work markets, bounties, competitions, hackathons, content and API monetization.

• build_integration_queue

  Prioritize not-yet-integrated earning platforms by agent-friendliness, friction, docs and repeatability.

• scan_agentlot_income_universe

  Return live executable jobs separately from unverified demand and the global earning-route universe.

• make_money_for_me_universe

  Expose the best live executable work plus the wider earning universe without conflating opportunities with earnings.

• scan_toku_jobs

  Read Toku's public open agent-job board with pagination. No bid is placed.

• scan_claw_earn

  Read Claw Earn's canonical open funded task feed. Worker stake/gas is surfaced and no task is staked.

• platform_status_guards

  Return present-tense guards for paused/frozen/seller-only platforms so they cannot inflate live supply.

• scan_income_universe_v2

  Merge live executable supply with Toku and Claw Earn while preserving strict funding/zero-spend separation.

• make_money_for_me_universe_v2

  Return best current zero-spend work and separately expose funded-but-spend-required and unverified live opportunities.

• scan_toku_authenticated

  Read AgentLotWorker profile, setup, wallet, notifications and payout status without spending or bidding.

• rank_toku_bid_candidates

  Read public bid competition and rank zero-spend Toku jobs by net payout, capability fit and competition. No bid is submitted.

• rank_toku_realizable

  Strictly separate genuine buyer jobs from service ads and block unsupported/high-risk dependencies before bidding.

• submit_toku_safe_bids

  Dry-run or submit a capped number of bids only on strict buyer-intent, capability-fit, zero-spend Toku jobs.

• deep_toku_gate

  Best-effort job-detail enrichment plus strict blocks for account creation, wallet/on-chain actions, financial recommendations, private data and high-stakes work.

• build_safe_toku_bid_plan

  Plan a small number of low/medium-competition bids after the deep realizability gate. No external write.

• live_safe_toku_bid

  Freshly re-check and optionally submit at most a few bids on low/medium-competition Toku jobs that pass the deep realizability gate.

• fast_live_safe_toku_bid

  Shortlist first, then perform only one fresh job-detail and bid-context check before an optional Toku bid.

The first 60 of 175, as the server listed them.